Run 4. Outer Step 43. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563347,
-    5563350,
-    5563355,
-    5563360,
-    5563364
+    5563369,
+    5563374,
+    5563378,
+    5563382,
+    5563386
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5560919,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd0bac75b97ef289e2d51b4684ebae45efabdcb285e0e503cb2fbb11b88689c
+oid sha256:a2dd07951fe59fdfb36c38b9b5d2ab7b11846841900ecce88aea9bedf6f776b4
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1546b7097b30edafa6cb7d2ee17e74c890adc7209dc98c2e519f3fab312f8635
+oid sha256:276107d7a0cc086c463273a12ab909fd2d51eba9331d66b3d180736839f0b8d7
 size 4040701744